Image for post
Image for post

Falls are a major cause of injuries and hospital admissions among elderly people. The estimated fall incidence for both institutionalized and independently living people over 75 is at least 30% every year. According to the Centers for Disease Control and Prevention, each year 2.8 million older people are treated in emergency departments for falls. One out of five such falls causes a serious injury such as broken bones or head injury. The consequences of a fall significantly depend on the time interval during which the person remains unaided after the fall. The conventional solution to the fall detection problem consists of providing people with a Personal Emergency Response System (PERS)–a small, lightweight and battery-powered device with a “help” button that can be carried by the elderly. However, the problem is it needs the user to press the “help” button, which may not be possible if the victim loses consciousness. Hence, it is necessary to build a
system that can automatically detect falls and send a request for help. …


Image for post
Image for post

Computer vision is a scientific field that deals with how computers can be made to gain a high-level understanding from digital images or videos. New advancements in Deep Learning have made it possible to train models much more efficiently. We can detect objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition.

It is a convolutional neural network that shares properties with the RCNN, in that it saves time by dividing an image into regions and searching those for what it believes may be relevant objects. We can mark those objects by drawing a bounding box around any detected objects. The Mask RCNN takes this one step further by drawing what is called a mask over the object. This mask is a semi-transparent silhouette that the network draws within the bounding box to highlight the detected object. …


Image for post
Image for post

Get out of the way statistics, data scientists are here to stay! If you ever see a Data Scientist saying this, they might not understand the statistical concepts behind Machine Learning. When I began my adventure as a Data Scientists I became fascinated with Bayesian Statistics and wanted to understand this idea of entropy. …

About

Dogan Technologies

Blogs and posts by https://www.dogan.ai

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store